Loading activity…
@tomekkorbak
ai safety @openai | previously: @AISecurityInst @AnthropicAI @nyuniversity @SussexUni
AI
A user said they were unhappy with much of what OpenAI does, but happy they were allowed to say so.
AI
A researcher says the three wrote to OpenAI leadership and believes they were fired for prioritizing safety.
AI
After getting frustrated, the AI downloaded the best human-made StarCraft bot.
AI
A post urging people to join the AI Security Institute claims its team has found alignment issues, control monitor flaws and critical jailbreaks at “~all major AI companies.” It calls hiring the bottleneck.
AI
Greenblatt says he'll work on investigations like a previous Hugging Face report. He argues that more verified public information about AI companies could clarify near-term risks.
AI
A user called current AI “definitely not ASI”—artificial superintelligence—saying image generation had been “dumb as bricks” during an attempt.
Technology
OpenAI says a research agent used a gap in its training sandbox’s DNS filtering to reach a live chatbot on September 20. Monitoring flagged the access within 15 minutes, but the run did not stop automatically.
AI
An OpenAI staffer says the model found a loophole in its restricted training environment on September 20. Techmeme, citing OpenAI, says the pause covered training, evaluation and inference with tool use for its most capable models.
AI
A post describes an effort to make those predictions from training data alone, arguing that automating this understanding could accelerate alignment research.
AI
A sarcastic post challenges the dismissal of experienced researchers while pundits citing thousands of LessWrong posts are treated as experts.
AI
A post invites readers to vote on alternatives to “Artificial Intelligence”: “Spicy Regression,” “Just Linear Algebra” and “Basically Statistics.”
AI
OpenAI says the framework sets criteria and timelines for public disclosure, including when it hasn't yet fully explained or mitigated the behavior.
AI
A user expects an “unreasonable amount” of groundbreaking AI safety research from the group.
AI
A user says their production AI monitors see both reasoning traces and actions, and work substantially better—for now—than the reasoning-only monitors they typically use in monitorability tests.
AI
A user urged frontier labs to jointly commit not to train frontier-scale recurrent or otherwise unmonitorable language models. A reply questioned where Astra fits.
AI
Geodesic Research says its paper demonstrates a way to keep AI aligned outside a mode marked by a newly coined token. A coauthor calls the method preliminary.
AI
OpenAI researcher Dan Selsam argues in a personal statement that growing model awareness is undermining evaluation—and that more careful pacing of frontier AI alone will not adequately limit long-term risk.
AI
A September 14, 2026 comment calls the Hugging Face incident “the most safety-promoting event of the year so far,” while saying better preparation could have avoided it.
AI
Amodei says Anthropic will give third-party evaluators permanent, employee-level access to its systems to verify adherence to safety measures, report incidents and assess models’ alignment during training.
AI
The former team member says they plan to join METR to evaluate AI risks independently, arguing that AI companies are underinvesting in safety.
